tokenizer_config.json

{
  "additional_special_tokens": [
    "À",
    "Á",
    "Â",
    "Ã",
    "Ä",
    "Å",
    "Æ"
  ],
  "bos_token": {
    "__type": "AddedToken",
    "content": "Å",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  },
  "clean_up_tokenization_spaces": true,
  "cls_token": {
    "__type": "AddedToken",
    "content": "Ä",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  },
  "eos_token": {
    "__type": "AddedToken",
    "content": "Æ",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  },
  "mask_token": {
    "__type": "AddedToken",
    "content": "Á",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  },
  "model_max_length": 128,
  "pad_token": {
    "__type": "AddedToken",
    "content": "Â",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  },
  "padding_side": "right",
  "sep_token": {
    "__type": "AddedToken",
    "content": "Ã",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  },
  "tokenizer_class": "PreTrainedTokenizerFast",
  "unk_token": {
    "__type": "AddedToken",
    "content": "À",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  }
}